Sökning: "matrix memory allocation"

Visar resultat 1 - 5 av 6 uppsatser innehållade orden matrix memory allocation.

1. 1. Recycling a non-contiguous matrix as workspace : Instance of packaging & cutting problem

   Kandidat-uppsats, Umeå universitet/Institutionen för datavetenskap

   Författare :Oscar Nilsson; [2023]
   Nyckelord :matrix; matrices; memory;

   Sammanfattning : This report explores a common issue in a system involving matrices, namely the mismatch between the allocation and deallocation ratios. This results in more matrices being allocated than deallocated, eventually leading to insufficient memory. The mismatch in the ratio is an implication of how matrices are normally used. LÄS MER

3. 2. AI Based Methods for Matrix Multiplication in High Resolution Simulations of Radio Access Networks

   Master-uppsats, KTH/Matematisk statistik

   Författare :Marcus Johnson; Herman Forslund; [2023]
   Nyckelord :Product-Quantization; MADDNESS; Radio Access Networks; Channel Estimation; MIMO; Approximate Matrix Multiplication; Pruduktkvantisering; MADDNESS; RAN; MIMO; Approximativa matrismultiplikation;

   Sammanfattning : The increasing demand for mobile data has placed significant strain on radio access networks (RANs), leading to a continuous need for increased network capacity. In keeping with that, a significant advancement in modern RANs is the ability to utilize several receivers and transmitters, to allow for beamforming. LÄS MER

4. 3. Register Caching for Energy Efficient GPGPU Tensor Core Computing

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Qiran Qian; [2023]
   Nyckelord :Computer Architecture; GPGPU; Tensor Core; GEMM; Energy Efficiency; Register File; Cache; Instruction Scheduling; Datorarkitektur; GPGPU; Tensor Core; GEMM; energieffektivitet; registerfil; cache; instruktionsschemaläggning;

   Sammanfattning : The General-Purpose GPU (GPGPU) has emerged as the predominant computing device for extensive parallel workloads in the fields of Artificial Intelligence (AI) and Scientific Computing, primarily owing to its adoption of the Single Instruction Multiple Thread architecture, which not only provides a wealth of thread context but also effectively hide the latencies exposed in the single threads executions. As computational demands have evolved, modern GPGPUs have incorporated specialized matrix engines, e. LÄS MER

5. 4. Adapting Marching Squares to operate on sparse matrices

   Kandidat-uppsats, Umeå universitet/Institutionen för datavetenskap

   Författare :Tahir Mert Karkan; [2022]
   Nyckelord :;

   Sammanfattning : Marching Squares is an algorithm that iterates over a given matrix filled with data points and outputs lines depending on the values in the grid. The algorithm iterates over the matrix four data points at a time in the shape of a square, hence its name. LÄS MER

7. 5. Klassiska populationsmodeller kontra stokastiska : En simuleringsstudie ur matematiskt och datalogiskt perspektiv

   Kandidat-uppsats, Matematiska och systemtekniska institutionen

   Författare :Mattias Nilsson; Ingela Jönsson; [2008]
   Nyckelord :stochastic simulation; population growth; population model; Malthus; exponential population growth; Verhulst; logistic population growth; Lotka-Volterra; diffusion approximation; birthdeath process; time optimization; C; MatLab; matrix memory allocation; MatLab clear; stokastisk simulering; populationstillväxt; populationsmodell; Malthus; exponentiell populationstillväxt; Verhulst; logistisk populationstillväxt; Lotka-Volterra; diffusionsapproximation; födelsedödsprocess; tidsoptimering; C; MatLab; matris minnesallokering; MatLab clear;

   Sammanfattning : I detta tvärvetenskapliga arbete studeras från den matematiska sidan tre klassiska populationsmodeller: Malthus tillväxtmodell, Verhulsts logistiska modell och Lotka-Volterras jägarebytesmodell. De klassiska modellerna jämförs med stokastiska. De stokastiska modeller som studeras är födelsedödsprocesser och deras diffusionsapproximation. LÄS MER